<p>Using The Apriori Algorithm To Classify The Care Needs Of Patients With Different Types Of Dementia</p>

(1)

O R I G I N A L R E S E A R C H

Using The Apriori Algorithm To Classify The Care

Needs Of Patients With Different Types Of Dementia

This article was published in the following Dove Press journal: Patient Preference and Adherence

Kai-Ming Jhang1,*

Ming-Che Chang2,*

Tzu-Ying Lo3

Che-Wei Lin4

Wen-Fu Wang1,5,*

Hsin-Hung Wu 3,6

1_{Department of Neurology, Changhua} Christian Hospital, Changhua, Taiwan; 2_{Department of Nuclear Medicine,} Changhua Christian Hospital, Changhua, Taiwan;3_{Department of Business} Administration, National Changhua University of Education, Changhua, Taiwan;4_{Medical Divisions of}

Performance Center, Changhua Christian Hospital, Changhua, Taiwan;

5_{Department of Holistic Wellness, Ming} Dao University, Changhua, Taiwan; 6_{Department of M-Commerce and} Multimedia Applications, Asia University, Taichung City, Taiwan

*These authors contributed equally to this work

Purpose:To elucidate speciﬁc combinations of care needs for people living with dementia

(PLWD) and their caregivers according to speciﬁc subtypes of dementia.

Patients and methods:A cross-sectional study at memory clinics in Changhua Christian Hospital, Taiwan, was conducted. Five hundred and eight people living with dementia and their caregivers joined the dementia collaborative care model. The care team established 15 care needs containing most of quality measures for PLWD and their caregivers. Individualized care plans including different combinations of care needs were addressed

through face-to-face assessments. Apriori algorithm was used to ﬁnd speciﬁc combinations

of care needs for particular groups of PLWD and their caregivers.

Results: This study identiﬁed the basic care needs of PLWD and caregivers including appropriate scheduling of activities, regular outpatient follow-up treatment, introduction and referral of social resources, referral to family support groups and care skills training, and health education for dementia and behavioral and psychological symptoms of dementia.

Patients with Alzheimer’s dementia required more care to prevent trafﬁc accidents and

getting lost, while patients with vascular dementia required more care to prevent falls. The

older (≥75 years old) PLWD were associated with more needs of fall prevention and care for

the mood of the caregiver, especially in the female patients with mild Alzheimer’s dementia

(CDR = 1).

Conclusion:Bundling the needed care needs might be a more effective means to care for a wide variety of patients with dementia.

Keywords: people living with dementia, behavioral and psychological symptoms of dementia, dementia collaborative care model, care need, Apriori algorithm

Introduction

Dementia is one of the greatest global challenges for health and social care in the

21st century.1While prevalence trajectories are unclear in high-income countries,

the number of people living with dementia (PLWD) continues to grow globally,

especially in low- and middle-income countries.2Some evidence supports that the

prevalence of dementia is increasing in East Asia.3,4

The number of older people in Taiwan has grown rapidly in the past decades, with the percentage of the population over the age of 65 years increasing from 6.8%

in 1992 to 14.1% in 2018.5 The prevalence of all-cause dementia in older

Taiwanese in 2014 was 8.04% according to a nationwide cross-sectional survey,

with an estimated 250,000 PLWD in 2018.6 PLWD need help with challenging

changes in behavior, cognition, and mood, and their caregivers often suffer from the

caregiving, depression and health problems.1,7

Correspondence: Hsin-Hung Wu No. 2 Shida Road, Changhua City 500, Taiwan

Tel +886 4 7232105 ext. 7412 Fax +886 4-7211292 Email [email protected]

Patient Preference and Adherence

Dove

press

open access to scientiﬁc and medical research

Open Access Full Text Article

Patient Preference and Adherence downloaded from https://www.dovepress.com/ by 118.70.13.36 on 26-Aug-2020

(2)

To address patients’and caregivers’complex healthcare needs, several collaborative care models have been published

in the last decade.8–11 These models are characterized by

interprofessional teams, multicomponent interventions, and shared decision-making between healthcare professionals

and patients as well as their caregivers.12Previous studies

have performed comprehensive patient-centered assessments

of PLWD and their care partners, including the patient’s

function, behavior and health status, and their challenges or

unmet needs.9,10The goal of a systematic assessment is to

identify opportunities to support personhood, reduce safety risks, optimize quality of life, and form team-approached

care planning.10Although still controversial, several studies

suggest that a collaborative approach improves the quality of care for patens with dementia, increases adherence to

demen-tia guidelines, and decreases behavioral problems.13–15

We established a dementia collaborative care model at Changhua Christian Hospital, a medical center in Changhua, Taiwan, in October 2014. The care team includes physicians (including neurologists, psychiatrists, gerontologists, and pri-mary care physicians), psychologists, social workers, dieti-cians, occupational therapists, pharmacists, and nursing case managers. This team performs patient and care partner inter-ventions when a diagnosis of dementia (including mild cog-nitive impairment (MCI) and very mild dementia) has been made. More than 95% of PLWD are community residents at

theﬁrst intervention. The cognition, function, living status,

home environment, behavior and psychological symptoms of the patient, as well as the stress, mood and preference of the caregiver are assessed through both telephone and face-to-face interviews. After team-approached assessments, an indi-vidualized care plan is formed. The care team addresses 15

different care needs (Table 1) containing most of quality

measures and needs for dementia patients and their

caregivers.9,10,12,16,17Care needs provide main care targets

and guide team members for subsequent follow-up. Each need is addressed when assessments are abnormal (e.g. if

the environment is unsafe or there are economic difﬁculties).

In clinical practice, the collaborative team observed that certain care needs often occur in combination and

that some occurred more frequently in people with speciﬁc

subtypes of dementia. Most previous studies have focused

on the prevalence of various care needs of dementia.18–20

However, no previous study has attempted to group or classify care needs. Grouping care needs for particular conditions such as the severity or subtype of dementia

would allow for more efﬁcient and holistic care.

Therefore, the aim of the present study was to elucidate

whether speciﬁc combinations of care needs can be

applied to particular groups of PLWD and their caregivers using the Apriori algorithm, as this algorithm can reveal interesting statistical correlations from a multidimensional viewpoint when each attribute is viewed as a dimension by

establishing threshold values of support and conﬁdence.21

Materials And Methods

Patients diagnosed as mild cognitive impairment or dementia at memory clinic from October 2015 to April 2017 in Changhua Christian Hospital were enrolled. The clinical trial was approved by the Institutional Review Board of Changhua Christian Hospital (CCH IRB 160165). Because the design of the present study was a retrospective chart review, informed consent was waived by the Institutional Review Board of Changhua Christian Hospital. All data were recorded in the electronic medical chart

with the highest conﬁdentiality and compliance with

the Declaration of Helsinki. Six hundred and eight patients who received team-approached assessment were screened, and after excluding those with incom-plete data and those with a dementia subtype including fewer than 10 registered patients, the remaining 508 were included for analysis. The demographic informa-tion including gender, age, type of dementia, and

clin-ical dementia rating (CDR) is summarized in Table 2.

A majority of the patients were women (66%)

with Alzheimer’s disease (72%) aged 75 years and

older (82%) who had mild dementia (51%).

National Institute on Aging-Alzheimer’s Association

(NIA-AA),22,23 International Society for Vascular

Behavioral and Cognitive disorders (VASCOG)24 and

Movement Disorder Society-Task force criteria were used for diagnosis of AD, vascular dementia and

Parkinson's disease dementia, respectively.25 Patients

ﬁt both possible AD by NIA-AA criteria and possible

major vascular cognitive disorder by VASCOG criteria

were classiﬁed as mixed dementia. The 15 care needs

listed in Table 1 were then assessed.

The purpose of this study was to identify whether

speciﬁc combinations of several care needs could be

applied to particular groups of PLWD and their caregivers

and thereby to provide more efﬁcient and holistic care.

That is, we intended to group the care needs for patients with dementia by gender, age, type of dementia, and dementia severity. The Apriori algorithm has been proven to be a very useful approach to discover previously

(3)

unknown interesting relationships in data sets by ﬁnding rules and associations between any of the attributes by

establishing support, conﬁdence, and lift, which are

deﬁned as follows.21,26,27 The support for an association

rule A ⇒ B is assessed by calculating the percentage of

transactions in the database containing both A and B:

Table 1Fifteen Care Needs Addressed By Changhua Christian Hospital

Number Description Contents

1 Adequate nutrition and diet This need was selected if the nutritional assessment was abnormal through evaluating a patient’s oral intake ability and recent body weight change. A nursing case manager or dietician gave individualized nutritional suggestions

2 Maintenance of personal hygiene This need was chosen if a patient’s activity of daily living was impaired. Care skills education and in-house reablement program were introduced

3 Appropriate schedule of activities This need was targeted if a patient’s daily physical activity was low. A nursing case manager would provide a daily schedule suggestion

4 Adequate sleep and rest This need was selected if poor sleep quality was recorded. The study team then provided sleep hygiene education and discussed the usage of sleep medication

5 Fall prevention This need was added if a risk of fall score located within a high-risk group. Physical training program and assistive devices evaluation were introduced

6 Preventing trafﬁc accidents and getting lost This need was chosen if a patient’s ambulatory function was preserved with the history of trafﬁc accident or getting lost due to a cognitive decline. A nursing case manager then provided the driving ability evaluation and assistive device for prevention of getting lost

7 Preventing misusage of medications This need was selected if misusage of medication was detected through asking residual drugs or from the care partner. Strategies including using drug boxes and decreasing use

frequency were suggested

8 Adjusting home environment safety This need was selected if any event of indoor safety concern has been recorded (eg, overcooked or burning). An experienced nurse or therapist then provided home environmental evaluation and adjustment

9 Regular outpatient follow-up treatment This need was added if a physician suggested a medication treatment. A case manager would follow the patient every month to maintain adherence

10 Behavioral and psychological symptoms of dementia (BPSD) treatment

This need was selected if presence of any BPSD, which was detected through neuropsychiatric inventory annually. Non-pharmacological treatments were givenﬁrst and pharmacological interventions were only reserved for severe patients

11 Referral to other specialists This need was added if any medical problem which needs other subspecialists was detected during the assessment

12 Introduction and referral of social resources This need was selected if PLWD and their caregivers asked social resources such as disability card, day care facilities, or guardianship

13 Referral to family support groups and care skills training

This need was chosen if a high Zarit’s caregiver burden score was recorded during the assessment. Support groups of dementia caregivers were introduced

14 Care for the mood of the caregiver This need was selected if a caregiver presented with depressive mood (screen by CES-D). The caregiver with the severe condition received emotional support and transferred to psychiatrist

15 Education for dementia and BPSD This need was chosen if PLWD and caregivers asked education information about dementia or BPSD, such as prevention, disease course, and medications. Different education programs were arranged according to the learning ability

Abbreviation:CES-D, Center for Epidemiologic Studies-Depression Scale.

(4)

Support¼P Að \BÞ

¼number of transactions containing both A and B

total number of transactions (1)

The conﬁdence of the association rule A⇒B is assessed by

evaluating the accuracy of the rule based on the calculation of the percentage of transactions in the database containing A and also containing B simultaneously:

Confidence¼P B Að j Þ¼P Að \BÞ

P Að Þ

¼number of transactions containing both A and B

number of transactions containing A (2)

Lift is a simple correlation measuring whether A and B are independent or dependent and correlated events as shown in Equation (3). If a rule has a lift of one, A and B are indepen-dent and no rule will be generated containing either event. If a rule has a lift greater than one, A and B are dependent and correlated positively. In practice, analysts tend to prefer rules

with either high support or high conﬁdence and usually

both.28In fact, strong rules will be found when certain

mini-mum support and conﬁdence conditions have been met.

Lift Að ;BÞ¼P Að \BÞ

P Að ÞP Bð Þ (3)

The Apriori algorithm in IBM SPSS Modeler 18 was used

in this study. The notations of data type deﬁned by

numerical values or abbreviations are depicted in Table 2.

The input variables for antecedents were gender, age, type of dementia, and CDR. The 15 care needs developed by our

hospital were classiﬁed as both antecedents and

conse-quents. The notations for each care need were 1 or 0. If a particular care need was applied to a patient, a value of 1 was assigned. If not, a value of 0 was used. This allowed for

the identiﬁcation of combinations of care needs. Minimum

support, minimum conﬁdence, and lift were set to 10%,

90%, and greater than one, respectively. The rules with higher support values indicated that the care need bundles could fulﬁll the majority of the patients’needs. In contrast, the rules with relatively lower support values indicated that the care need bundles may only be applicable to a small portion of the patients, ie, special needs. The settings of antecedents and consequents in the Apriori algorithm allow the decision-maker to identify what combinations of care

needs would be needed according to the speciﬁc

demo-graphic information of the patients.

Results

A total of 1759 rules were generated by the Apriori

algo-rithm (Table 3 lists a sample of some of the rules). For

instance, Rule 1 indicated that a patient aged 70–74 years

required education for dementia and BPSD (Care (15)). Rule 2 showed that preventing the misuse of medications (Care (7)) and Care (15) should be bundled together to meet the needs of the patient. Rule 3 depicted that a patient

with Alzheimer’s disease needed Care (7) and the

intro-duction and referral of social resources (Care (12)). In Rule 4, a patient with moderate dementia needed both fall prevention (Care (5)) and also education for dementia and BPSD (Care (15)). Rule 5 suggested that Care (7), Care (12), and Care (9) (regular outpatient follow-up treat-ment) should be combined with Care (15). Of note,

con-ﬁdence in Rule 5 was 100%, showing that these four rules

could deﬁnitely be bundled for patients with dementia.

Moreover, in Rule 6, the combination of Care (13), Care (12), Care (3), Care (15), and Care (9) could meet the needs of 53.54% of the PLWD.

In order to categorize the rules effectively, the 1759 rules were divided into four categories in terms of different support values, ie, 40% and above, 30% but less than 40%, 20% but less than 30%, and 10% but less than 20%. Rules

that had both high support and conﬁdence values could be

viewed as the basic requirements for PLWD. That is, the

identiﬁed care needs could be bundled as a portfolio for

PLWD at the ﬁrst intervention. In contrast, rules with

Table 2Information Of The Patients With Dementia

Variables Frequency Percentage Data

Type

Gender Male 175 34 M

Female 333 66 F

Age Less than 65 years

old

17 3 0

65–69 years old 20 4 1

70–74 years old 56 11 2

75–79 years old 147 29 3

80–84 years old 145 29 4

85 years old and

above

123 24 5

Type of

dementia

Alzheimer’s disease 363 72 AD

Parkinson’s disease 26 5 PDD

Vascular dementia 93 18 VaD

Mixed dementia 26 5 MD

CDR Very mild dementia 104 21 0

Mild dementia 260 51 1

Moderate dementia 89 18 2

Severe dementia 55 11 3

Abbreviation:CDR, clinical dementia rating.

(5)

lower support but high conﬁdence values could be con-sidered as special needs for a very small group of PLWD.

With support of 40% and above, ﬁve basic care needs

were identiﬁed for the majority of the patients, including

appropriate scheduling of activities (Care (3)), regular out-patient follow-up treatment (Care (9)), introduction and referral of social resources (Care (12)), referral to family support groups and care skills training (Care (13)), and education for dementia and BPSD (Care (15)). With

sup-port of 30% but less than 40%, in addition to theﬁve basic

care needs for the majority of the patients, four additional

care needs were identiﬁed, including adequate sleep and

rest (Care (4)), preventing trafﬁc accidents and getting lost

(Care (6)), adjusting home environment safety (Care (8)), and care for the mood of the caregiver (Care (14)).

When the support was 20% but less than 30%, three

generalized rules were identiﬁed as shown inTable 4. The

ﬁrst generalized rule indicated that a patient with

Alzheimer’s disease who required the ﬁve basic care

needs should further receive interventions to prevent

traf-ﬁc accidents and getting lost (Care (6)). The second

gen-eralized rule indicated that a patient with Alzheimer's disease is required to focus on fall prevention (Care (5))

in addition to theﬁve basic care needs. Moreover, the third

generalized rule depicted that a patient with mild dementia needs to further focus on fall prevention (Care (5)). That is, the caregiver was required to pay extra attention to

prevent trafﬁc accidents and getting lost as well as fall

prevention for a patient with Alzheimer’s disease.

With support of 10% but less than 20%, nine

general-ized rules were identiﬁed as shown inTable 5. The ﬁrst

generalized rule indicated that a patient with vascular dementia needed additional interventions to prevent

falls (Care (5)) in addition to the ﬁve basic care needs.

In the second generalized rule, a patient with moderate

Alzheimer’s disease was required to the ﬁve basic care

needs. In the third generalized rule, with the conﬁdence

value of 100%, a female patient aged 75–79 years with

Alzheimer’s disease was required to receive theﬁve basic

care needs. The fourth generalized rule said that a patient with moderate dementia needed additional interventions

to prevent falls (Care (5)) in addition to the ﬁve basic

needs. In contrast, a female patient with moderate demen-tia was required to concentrate on Care (9) and Care (15)

of theﬁve basic care needs as shown in theﬁfth

general-ized rule. In the sixth generalgeneral-ized rule, a female patient

aged 75–79 years is required to haveﬁve basic care needs

with a conﬁdence value of 100%. In contrast to the sixth

generalized rule, the seventh rule showed that patients

aged 75–79 years required theﬁve basic care needs with

a conﬁdence value of 100%, and the caregiver’s stress

and mood should also be monitored (Care (14)). That is, the caregivers may suffer from the caregiving, depres-sion, and health problems when caring for patients aged

75–79 years. The eighth generalized rule indicated that

the patients with mild dementia aged 80–84 years

required additional interventions for fall prevention

(Care (5)) in addition to theﬁve basic care needs with a

Table 3Information Of The Patients With Dementia

Rule No. Antecedent Consequent No. Of Cases

In The Database

Support (%) Conﬁdence (%) Lift

1 Age = 2 Care (15) = 1 56 11.02 98.21 1.04

2 Care (7) = 1 Care (15) = 1 66 12.99 98.49 1.04

3 Care (7) = 1 Care (12) = 1 51 10.04 90.20 1.12

Type = AD

4 CDR = 2 Care (15) = 1 51 10.04 96.08 1.01

Care (5) = 1

5 Care (7) = 1 Care (15) = 1 51 10.04 100.00 1.05

Care (12) = 1 Care (9) = 1

6 Care (13) = 1 Care (9) = 1 272 53.54 91.54 1.04

Care (12) = 1 Care (3) = 1 Care (15) = 1

(6)

Table 4Three Generalized Rules With Support Of 20% But Less Than 30%

Rule Antecedent Consequent No. Of Cases In The Database Support (%) Conﬁdence (%) Lift

1 Care (6) = 1 Care (15) = 1 108 21.26 98.15 1.03

Type = AD Care (9) = 1

Care (6) = 1 Care (15) = 1 121 23.82 96.69 1.02

Type = AD

Care (6) = 1 Care (15) = 1 113 22.24 96.46 1.02

Care (6) = 1 Care (12) = 1 121 23.82 93.39 1.16

Type = AD

Care (6) = 1 Care (12) = 1 117 23.03 93.16 1.15

Care (6) = 1 Care (12) = 1 108 21.26 92.59 1.15

Care (6) = 1 Care (12) = 1 106 20.87 92.45 1.15

Type = AD Care (9) = 1 Care (15) = 1

Care (6) = 1 Care (9) = 1 117 23.03 90.60 1.03

2 Care (5) = 1 Care (15) = 1 114 22.44 96.49 1.02

Care (5) = 1 Care (15) = 1 113 22.24 96.46 1.02

Care (5) = 1 Care (15) = 1 130 25.59 96.15 1.01

Type = AD

Care (5) = 1 Care (9) = 1 104 20.47 90.39 1.03

3 Care (5) = 1 Care (15) = 1 111 21.85 96.40 1.02

CDR = 1

Care (5) = 1 Care (15) = 1 102 20.08 96.08 1.01

CDR = 1 Care (9) = 1

Care (5) = 1 Care (9) = 1 111 21.85 91.89 1.04

CDR = 1

Care (5) = 1 Care (9) = 1 107 21.06 91.59 1.04

CDR = 1 Care (15) = 1

(7)

Table 5Nine Generalized Rules With The Support Of 10% But Less Than 20%

1 Type = VaD Care (15) = 1 70 13.780 95.71 1.01

Care (12) = 1

Type = VaD Care (15) = 1 52 10.24 98.08 1.03

Care (12) = 1 Care (3) = 1

Type = VaD Care (15) = 1 62 12.21 96.77 1.02

Care (12) = 1 Care (9) = 1

Type = VaD Care (15) = 1 60 11.81 95.00 1.01

Care (13) = 1 Care (12) = 1

Type = VaD Care (9) = 1 60 11.81 91.67 1.04

Care (13) = 1 Care (12) = 1

Type = VaD Care (9) = 1 57 11.22 92.98 1.05

Care (13) = 1 Care (12) = 1 Care (15) = 1

Type = VaD Care (15) = 1 55 10.83 96.36 1.02

Care (13) = 1 Care (12) = 1 Care (9) = 1

Type = VaD Care (9) = 1 64 12.60 90.63 1.03

Care (13) = 1 Care (15) = 1

Type = VaD Care (12) = 1 58 11.42 91.38 1.13

Care (13) = 1 Care (9) = 1 Care (15) = 1

Type = VaD Care (15) = 1 65 12.80 96.92 1.02

Care (3) = 1

Type = VaD Care (15) = 1 58 11.42 96.55 1.02

Care (3) = 1 Care (9) = 1

Type = VaD Care (9) = 1 51 10.04 92.16 1.05

Care (5) = 1

2 CDR = 2 Care (15) = 1 57 11.22 96.49 1.02

CDR = 2 Care (15) = 1 57 11.22 98.25 1.04

CDR = 2 Care (15) = 1 55 10.83 96.36 1.02

CDR = 2 Care (15) = 1 66 12.99 96.97 1.02

Type = AD

(Continued)

(8)

Table 5(Continued).

3 Age = 3

Gender = F

Care (15) = 1 60 11.81 100 1.05

Type = AD Care (12) = 1 Care (3) = 1

Age = 3 Care (15) = 1 70 13.78 100 1.05

Gender = F Type = AD Care (12) = 1 Care (9) = 1

Age = 3 Care (15) = 1 64 12.60 100 1.05

Age = 3 Care (15) = 1 55 10.83 100 1.05

Age = 3 Care (15) = 1 64 12.60 100 1.05

4 CDR = 2 Care (15) = 1 51 10.04 96.08 1.01

Care (5) = 1

CDR = 2 Care (9) = 1 51 10.04 90.20 1.02

Care (5) = 1

5 CDR = 2 Care (9) = 1 53 10.43 90.57 1.03

Gender = F Care (15) = 1

CDR = 2 Care (15) = 1 54 10.63 98.15 1.03

Gender = F

CDR = 2 Care (9) = 1 54 10.63 90.74 1.03

Gender = F

6 Age = 3 Care (15) = 1 64 12.60 100 1.05

Gender = F Care (12) = 1 Care (3) = 1 Care (9) = 1

Age = 3 Care (15) = 1 61 12.01 100 1.05

Gender = F Care (13) = 1 Care (3) = 1 Care (9) = 1

(Continued)

(9)

Table 5(Continued).

7 Age = 3 Care (15) = 1 78 15.35 100 1.05

Care (13) = 1 Care (12) = 1 Care (3) = 1 Care (9) = 1

Age = 3 Care (15) = 1 85 16.73 100 1.05

Care (13) = 1 Care (3) = 1 Care (9) = 1

Age = 3 Care (15) = 1 51 10.04 100 1.05

Care (14) = 1 Care (13) = 1 Care (3) = 1

Age = 3 Care (15) = 1 62 12.21 100 1.05

Care (14) = 1 Care (3) = 1

Age = 3 Care (15) = 1 54 10.63 100 1.05

Care (14) = 1 Care (3) = 1 Care (9) = 1

Age = 3 Care (15) = 1 53 10.43 100 1.05

Care (14) = 1 Type = AD Care (9) = 1

8 Age = 4 Care (15) = 1 63 12.40 100 1.05

CDR = 1 Care (13) = 1

Age = 4 Care (15) = 1 55 10.83 100 1.05

CDR = 1 Care (13) = 1 Care (12) = 1

Age = 4 Care (15) = 1 51 10.04 100 1.05

CDR = 1 Care (13) = 1 Care (12) = 1 Care (3) = 1

Age = 4 Care (15) = 1 57 11.22 100 1.05

CDR = 1 Care (13) = 1 Care (3) = 1

Age = 4 Care (15) = 1 53 10.43 100 1.05

CDR = 1 Care (13) = 1 Care (3) = 1 Care (9) = 1

Age = 4 Care (15) = 1 58 11.42 100 1.05

CDR = 1 Care (13) = 1 Care (9) = 1

(Continued)

(10)

conﬁdence value of 100%. Given that the third, sixth,

seventh, and eighth generalized rules had 100% conﬁ

-dence, the ﬁve basic care needs were required for the

PLWD aged 75 years and older. Moreover, fall preven-tion and caring for the mood of the caregiver were also essential care needs.

Table 5(Continued).

Age = 4 Care (15) = 1 57 11.22 100 1.05

Care (5) = 1 Care (3) = 1

9 Care (8) = 1 Care (15) = 1 97 19.09 100 1.05

Care (12) = 1 Care (3) = 1 Care (9) = 1

Care (8) = 1 Care (15) = 1 90 17.72 100 1.05

Care (13) = 1 Care (12) = 1 Care (3) = 1

Care (8) = 1 Care (15) = 1 80 15.75 100 1.05

Care (8) = 1 Care (15) = 1 56 11.02 100 1.05

Care (14) = 1 Care (12) = 1 Care (3) = 1

Care (8) = 1 Care (15) = 1 59 11.61 100 1.05

Care (14) = 1 Care (3) = 1 Care (9) = 1

Care (6) = 1 Care (15) = 1 52 10.24 100 1.05

Care (8) = 1 Care (12) = 1 Care (3) = 1

Care (6) = 1 Care (15) = 1 51 10.04 100 1.05

Care (6) = 1 Care (15) = 1 59 11.61 100 1.05

Care (8) = 1 Care (12) = 1 Care (9) = 1

Care (6) = 1 Care (15) = 1 51 10.04 100 1.05

Care (8) = 1 Care (13) = 1 Care (12) = 1

Care (6) = 1 Care (15) = 1 57 11.22 100 1.05

Care (8) = 1 Care (3) = 1 Care (9) = 1

(11)

The ninth generalized rule further considered

prevent-ing trafﬁc accidents and getting lost (Care (6)) and

adjust-ing home environment safety (Care (8)) or adjustadjust-ing home environment safety and care for the mood of the caregiver

(Care (14)) in addition to the ﬁve basic care needs. In

practice, Care (6), Care (8), and Care (14) could be bundled together. Although the generalized rule had a relatively lower support value, the consequent care need was indicated when the antecedent care needs had a

con-ﬁdence value of 100%. Bundling the care needs may be a

more effective means to care for patients with dementia.

Discussion

To the best of our knowledge, this is the ﬁrst study to

extensively evaluate the care needs of PLWD and their caregivers and to differentiate them according to the sever-ity and subtype of dementia. The most common combina-tions of care needs were appropriate scheduling of activities, regular outpatient follow-up treatment, introduc-tion and referral of social resources, referral to family support groups and care skills training, and education for dementia and BPSD. These needs occurred frequently and

simultaneously with one another. Black et al18 reported

that the most common unmet needs of community-residing PLWD were safety, followed by meaningful activities, and medical care. For the caregivers, more than 85% had unmet needs of resource referral and education. Eichler

et al19 reported that the most frequent unmet needs of

patients with primary care dementia were nursing treat-ment and care, social counseling and legal support, and pharmaceutical treatment and care. The results of the pre-sent study are consistent with those of the previous studies and further strengthened the fundamental role of these

needs. The ﬁve basic needs can be viewed as basic care

needs for PLWD and their care partners, and a

collabora-tive team should consider these needs asﬁrst priority care.

Other less frequent combinations were preventing

traf-ﬁc accidents and getting lost, adjusting home environment

safety, and caring for the mood of the caregiver. When one of the care needs was selected, the others were usually also present. Our previous study showed that caregivers have the highest burden when taking care of patients who do not need help with daily activities (that is, they can walk

around and do housework).27 PLWD have a high risk of

getting lost and having household emergencies if they still have the ability to perform daily activities, which then

increases the caregiver’s burden. This suggests that if

one of the needs is unmet, case managers should pay more attention to the other two care needs.

The present study also found that the care needs were

different for speciﬁc subtypes and severity of dementia.

Except for the ﬁve basic care needs, patients with

Alzheimer’s dementia had needs for preventing trafﬁc

acci-dents and getting lost and fall prevention, while patients with vascular dementia needed more attention for fall prevention.

The older (≥75 years old) PLWD were associated with more

needs of fall prevention and care for the mood of the caregiver,

especially in the female patients with mild Alzheimer’s

dementia (CDR = 1). Whereas, patients with moderate demen-tia (CDR = 2) were associated with greater needs of fall

prevention, particularly in female patients with Alzheimer’s

dementia. Previous studies have discussed the different care needs of patients with mild cognitive impairment or dementia

and for those with young onset dementia.20,29However, only a

few studies have focused on care needs for speciﬁc types of

dementia, and studies on the care needs speciﬁc for patients

with vascular cognitive impairment are lacking.30,31Currently,

no studies have compared the care needs for patients with different etiologies of dementia. The present study highlights the shortage of related research and provides a future direction for research.

The strengths of this study include that it provides a more comprehensive viewpoint by combining various care

needs using a scientiﬁc method. Most previous studies

have only shown the percentage of each unmet need for

PLWD and their caregivers.18–20 Through the identiﬁ

ca-tion of the most common care needs, collaborative team

members can understand the care focus more efﬁciently,

especially for elementary dementia case managers.

Another strength is the Apriori algorithm combining var-ious variables to identify the care needs for particular

conditions. Unlike previous studies such as Black et al18

and Eichler et al19 which only evaluated one or more

variables causing a higher degree of unmet needs, our results provide a more clear scenario. For example, the appropriate care needs for elderly female PLWD with

mild-stage Alzheimer’s disease were appropriate

schedul-ing of activities, regular outpatient follow-up treatment, education for dementia and BPSD, and fall prevention. Care needs for their caregivers were introduction and referral of social resources, referral to family support groups and care skills training, and care for their mood.

This study did not include some care needs of dementia that have been reported in past reviews, including early dementia evaluation and diagnosis and advanced care

(12)

planning.9,17Because of the convenience and accessibility to medical care in Taiwan, PLWD and their care partners have easy access to subspecialists, especially in urban areas. People with suspected dementia usually receive a

ﬁnal etiological diagnosis within 1 month after complete

evaluations. Therefore, early dementia evaluation and diagnosis were not considered as care needs for the PLWD and caregivers in this study. Advanced care plan-ning is an important care need in patients with incurable chronic illnesses. The Patient Autonomy Act was passed in December 2015 in Taiwan and has been enforced since January 2019, which safeguards the medical autonomy and end-of-life rights of Taiwanese residents. In our site, the advanced care planning has been implemented for every PLWD who can name a surrogate decision-maker since 2016. Because our collaborative care model was imple-mented in October 2014, the advanced care planning was not selected as one of the care needs for dementia.

The quality measures and needs for patients with MCI were still unclear. However, American Academy of

Neurology practice guideline32 for MCI highlighted the

importance of the assessment and treatment of BPSD,

ﬁnancial and driving safety evaluation, and treatment and

prognosis education in MCI patients. Therefore, the pre-sent study included MCI patients with a suspected etiology according to the best opinion at diagnosis and provided collaborative care. Only 5% of the subjects had Lewy body disease, and none had frontotemporal dementia in the present study. Further studies are needed to investigate the care needs of people with those subtypes of dementia.

The present study did not include caregiver’s

characteris-tics, which may also have inﬂuenced the care needs.33

Limitation

The Apriori algorithm, which is one of the most commonly seen association rules, has been widely used to discover previously unknown interesting relationships in data sets by

ﬁnding rules and associations between any of the attributes

by establishing support, conﬁdence, and lift. However, there

are some limitations when the Apriori algorithm is used. First, there is no universal approach to set up support and

conﬁdence values in order to generate association rules. In

general, a higher conﬁdence value, say 90% or above, is

recommended when a conditional probability is applied to

study the associations of attributes. In contrast to conﬁ

-dence, setting a higher support value would reduce the number of rules that might result in missing some essential rules with low frequencies, ie, lower support values. On the

other hand, setting a lower support value could result in a large number of rules that might hinder the management to summarize rules because rules should be examined manu-ally to determine whether or not they are meaningful. Therefore, there is a trade-off between higher or lower support values. Second, the Apriori algorithm could be viewed as a screening approach to identify associations among a wide variety of attributes by setting up support

and conﬁdence values. Other approaches such as decision

trees can be applied to reduce ambiguity in a

decision-making process by assigning speciﬁc values to the problem,

decisions, and outcomes of each decision.

Conclusion

Most previous studies have focused on the percentage of each unmet need for patients with dementia and their

care-givers, however no studies have classiﬁed care needs.18–20

Grouping care needs according to the severity or subtype of

dementia may allow for more efﬁcient and holistic care.

This study used the Apriori algorithm to elucidate whether care needs can be bundled to meet the needs of particular

groups of PLWD and their caregivers and identiﬁed the

basic care needs including appropriate scheduling of activ-ities, regular outpatient follow-up treatment, introduction and referral of social resources, referral to family support groups and care skills training, and education for dementia

and BPSD. In addition, patients with Alzheimer’s dementia

required more care to prevent trafﬁc accidents and getting

lost as well as fall prevention, while patients with vascular dementia required more care to prevent falls. Bundling care needs may be a more effective means to care for a wide variety of patients with dementia.

Author Contributions

All authors contributed to data analysis, drafting or revising

the article, gaveﬁnal approval of the version to be published,

and agree to be accountable for all aspects of the work.

Disclosure

The authors report no conﬂicts of interest in this work.

References

1. Livingston G, Sommerlad A, Orgeta V, et al. Dementia prevention, intervention, and care. Lancet. 2017;390(10113):2673–2734. doi:10.1016/S0140-6736(17)31363-6

2. Prince M, Bryce R, Albanese E, Wimo A, Ribeiro W, Ferri CP. The global prevalence of dementia: a systematic review and metaanalysis. Alzheimers Dement.2013;9(1):63–75e2. doi:10.1016/j.jalz.2012.11.007

(13)

3. Prince M, Ali G-C, Guerchet M, Prina AM, Albanese E, Wu Y-T. Recent global trends in the prevalence and incidence of dementia, and survival with dementia. Alzheimer’s Res Ther. 2016;8(1):23. doi:10.1186/s13195-016-0188-8

4. Wu YT, Lee HY, Norton S, et al. Prevalence studies of dementia in mainland China, Hong Kong and Taiwan: a systematic review and meta-analysis. PLoS One. 2013;8(6):e66252. doi:10.1371/journal. pone.0066252

5. Statistical Yearbook of Interior2018. Available from:https://www.moi. gov.tw/stat/news_detail.aspx?sn=13742. Accessed June 13,2019. 6. Sun Y, Lee HJ, Yang SC, et al. A nationwide survey of mild cognitive

impairment and dementia, including very mild dementia, in Taiwan. PLoS One.2014;9(6):e100303. doi:10.1371/journal.pone.0100303 7. van der Roest HG, Meiland FJ, Maroccini R, Comijs HC, Jonker C,

Dröes RM. Subjective needs of people with dementia: a review of the literature. Int Psychogeriatr. 2007;19(3):559–592. doi:10.1017/ S1041610206004716

8. Austrom MG, Carvell CA, Alder CA, Gao S, Boustani M, LaMantia M. Workforce development to provide person-centered care. Aging Ment Health.2016;20(8):781–792. doi:10.1080/13607863.2015.1119802 9. Khanassov V, Vedel I. Family physician-case manager collaboration

and needs of patients with dementia and their caregivers: a systematic mixed studies review. Ann Fam Med. 2016;14(2):166–177. doi:10.1370/afm.1898

10. Molony SL, Kolanowski A, Van Haitsma K, Rooney KE. Person-centered assessment and care planning. Gerontologist. 2018;58 (suppl_1):S32–S47. doi:10.1093/geront/gnx173

11. Reilly S, Miranda-Castillo C, Malouf R, et al. Case management approaches to home support for people with dementia. Cochrane Database Syst Rev.2015;5(1):CD008345.

12. Dreier-Wolfgramm A, Michalowsky B, Austrom MG, et al. Dementia care management in primary care : current collaborative care models and the case for interprofessional education. Z Gerontol Geriatr. 2017;50(Suppl 2):68–77. doi:10.1007/s00391-017-1220-8

13. Ganz DA, Koretz BK, Bail JK, et al. Nurse practitioner comanage-ment for patients in an academic geriatric practice. Am J Manag Care.2010;16(12):e343–e355.

14. Vickrey BG, Mittman BS, Connor KI, et al. The effect of a disease management intervention on quality and outcomes of dementia care: a randomized, controlled trial.Ann Intern Med.2006;145(10):713– 726. doi:10.7326/0003-4819-145-10-200611210-00004

15. Callahan CM, Boustani MA, Unverzagt FW, et al. Effectiveness of collaborative care for older adults with Alzheimer disease in primary care: a randomized controlled trial.JAMA.2006;295(18):2148–2157. doi:10.1001/jama.295.18.2148

16. Hsu YY, Chen FM, Wang WF, Lin CW, Wu HH. Using classiﬁcation and regression tree to identify care target combinations for different dementia patients from a medical center in Taiwan.J Med Imag Health In.2018;8(4):701–705.

17. Sanders AE, Nininger J, Absher J, Bennett A, Shugarman S, Roca R. Quality improvement in neurology: dementia management quality measurement set update. Neurology. 2017;88(20):1951–1957. doi:10.1212/WNL.0000000000003917

18. Black BS, Johnston D, Rabins PV, Morrison A, Lyketsos C, Samus QM. Unmet needs of community-residing persons with dementia and their informal caregivers:ﬁndings from the maximizing indepen-dence at home study. J Am Geriatr Soc. 2013;61(12):2087–2095. doi:10.1111/jgs.12549

19. Eichler T, Thyrian JR, Hertel J, et al. Unmet needs of community-dwelling primary care patients with dementia in Germany: prevalence and correlates.J Alzheimers Dis.2016;51(3):847–855. doi:10.3233/ JAD-150935

20. Johnston D, Samus QM, Morrison A, et al. Identiﬁcation of commu-nity-residing individuals with dementia and their unmet needs for care. Int J Geriatr Psychiatry. 2011;26(3):292–298. doi:10.1002/ gps.2527

21. Han J, Kamber M.Data Mining: Concepts and Techniques. 2nd ed. New York: Morgan Kaufmann Publishers;2006.

22. Albert MS, DeKosky ST, Dickson D, et al. The diagnosis of mild cognitive impairment due to Alzheimer’s disease: recommendations from the National Institute on Aging-Alzheimer’s Association work-groups on diagnostic guidelines for Alzheimer’s disease.Alzheimers Dement.2011;7(3):270–279. doi:10.1016/j.jalz.2011.03.008 23. McKhann GM, Knopman DS, Chertkow H, et al. The diagnosis of

dementia due to Alzheimer’s disease: recommendations from the National Institute on Aging-Alzheimer’s Association workgroups on diagnostic guidelines for Alzheimer’s disease.Alzheimers Dement. 2011;7(3):263–269. doi:10.1016/j.jalz.2011.03.005

24. Sachdev P, Kalaria R, O’Brien J, et al. Diagnostic criteria for vascular cognitive disorders: a VASCOG statement. Alzheimer Dis Assoc Disord.2014;28(3):206–218. doi:10.1097/WAD.0000000000000034 25. Emre M, Aarsland D, Brown R, et al. Clinical diagnostic criteria for

dementia associated with Parkinson’s disease.Mov Disord.2007;22 (12):1689–1707. doi:10.1002/mds.21507

26. Lee YC, Huang CH, Lin YC, Wu HH. Association rule mining to Identify critical demographic variables inﬂuencing the degree of burnout in a regional teaching hospital.Tem J.2017;6(3):497–502. 27. Yan GJ, Wang WF, Jhang KM, Lin CW, Wu HH. Association

between patients with dementia and high caregiving burden for caregivers from a medical center in Taiwan. Psychol Res Behav Manag.2019;12:55–65. doi:10.2147/PRBM.S187676

28. Larose DT.Discovering Knowledge in Data: An Introduction to Data Mining. Hoboken, NJ: John Wiley and Sons;2005.

29. Millenaar JK, Bakker C, Koopmans RT, Verhey FR, Kurz A, de Vugt ME. The care needs and experiences with the use of services of people with young-onset dementia and their caregivers: a sys-tematic review.Int J Geriatr Psychiatry.2016;31(12):1261–1276. doi:10.1002/gps.4502

30. Goldman JG, Vernaleo BA, Camicioli R, et al. Cognitive impair-ment in Parkinson’s disease: a report from a multidisciplinary symposium on unmet needs and future directions to maintain cognitive health. NPJ Parkinsons Dis. 2018;4:19. doi:10.1038/ s41531-018-0055-3

31. Galvin JE, Duda JE, Kaufer DI, Lippa CF, Taylor A, Zarit SH. Lewy body dementia: caregiver burden and unmet needs.Alzheimer Dis Assoc Disord. 2010;24(2):177–181. doi:10.1097/WAD.0b013e3181c72b5d

32. Petersen RC, Lopez O, Armstrong MJ, et al. Practice guideline update summary: mild cognitive impairment: report of the guideline development, dissemination, and implementation subcommittee of the American Academy of Neurology.Neurology.2018;90(3):126– 135. doi:10.1212/WNL.0000000000004826

33. Wawrziczny E, Pasquier F, Ducharme F, Kergoat MJ, Antoine P. Do spouse caregivers of young and older persons with dementia have different needs? A comparative study. Psychogeriatrics. 2017;17 (5):282–291. doi:10.1111/psyg.12234

(14)

Patient Preference and Adherence

Dove

press

Publish your work in this journal

Patient Preference and Adherence is an international, peer-reviewed, open access journal that focusing on the growing importance of patient preference and adherence throughout the therapeutic conti-nuum. Patient satisfaction, acceptability, quality of life, compliance, persistence and their role in developing new therapeutic modalities and compounds to optimize clinical outcomes for existing disease

states are major areas of interest for the journal. This journal has been accepted for indexing on PubMed Central. The manuscript management system is completely online and includes a very quick and fair peer-review system, which is all easy to use. Visit http:// www.dovepress.com/testimonials.php to read real quotes from pub-lished authors.

Submit your manuscript here:https://www.dovepress.com/patient-preference-and-adherence-journal